9th Annual Conference of the International Speech Communication Association

Brisbane, Australia
September 22-26, 2008

Confusion-Based Entropy-Weighted Decoding for Robust Speech Recognition

Yi Chen, Chia-yu Wan, Lin-shan Lee

National Taiwan University, Taiwan

An entropy-based feature parameter weighting scheme was proposed previously [1], in which the scores obtained from different feature parameters are weighted differently in the decoding process according to an entropy measure. In this paper, we propose a more delicate entropy measure for this purpose considering the inherent confusion among different acoustic classes. If a set of acoustic classes are easily confused, those feature parameters which can distinguish them should be emphasized. Extensive experiments with the Aurora 2 testing environment verified that this approach is equally useful for different types of features, and can be easily integrated with typical existing robust speech recognition approaches.


  1. Y. Chen, C.-Y. Wan, L.-S. Lee, "Entropy-Based Feature Parameter Weighting for Robust Speech Recognition," ICASSP 2006.

Full Paper

Bibliographic reference.  Chen, Yi / Wan, Chia-yu / Lee, Lin-shan (2008): "Confusion-based entropy-weighted decoding for robust speech recognition", In INTERSPEECH-2008, 1008-1011.